Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1391 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.4106. Min Act: -0.0000

Data Index: 833377 (The Pile)

Max Activating Token Index: 630

Text #1

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.4133. Min Act: -0.0000

Data Index: 610722 (The Pile)

Max Activating Token Index: 274

Text #2

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.4014. Min Act: -0.0000

Data Index: 1573564 (The Pile)

Max Activating Token Index: 484

Text #3

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.3927. Min Act: -0.0000

Data Index: 820405 (The Pile)

Max Activating Token Index: 411

Text #4

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.3718. Min Act: -0.0000

Data Index: 337887 (The Pile)

Max Activating Token Index: 21

Text #5

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.3638. Min Act: 0.0000

Data Index: 1756589 (The Pile)

Max Activating Token Index: 957

Text #6

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.3380. Min Act: -0.0000

Data Index: 1644130 (The Pile)

Max Activating Token Index: 429

Text #7

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.3499. Min Act: -0.0000

Data Index: 386417 (The Pile)

Max Activating Token Index: 719

Text #8

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.3394. Min Act: 0.0000

Data Index: 1154123 (The Pile)

Max Activating Token Index: 136

Text #9

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.3175. Min Act: -0.0000

Data Index: 1457124 (The Pile)

Max Activating Token Index: 641

Text #10

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.2925. Min Act: -0.0000

Data Index: 1277513 (The Pile)

Max Activating Token Index: 1016

Text #11

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.3059. Min Act: -0.0000

Data Index: 563431 (The Pile)

Max Activating Token Index: 161

Text #12

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.2798. Min Act: -0.0000

Data Index: 714577 (The Pile)

Max Activating Token Index: 106

Text #13

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.2737. Min Act: 0.0000

Data Index: 57660 (The Pile)

Max Activating Token Index: 150

Text #14

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.2918. Min Act: -0.0000

Data Index: 897342 (The Pile)

Max Activating Token Index: 269

Text #15

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.3180. Min Act: -0.0000

Data Index: 259400 (The Pile)

Max Activating Token Index: 736

Text #16

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.2603. Min Act: 0.0000

Data Index: 1287861 (The Pile)

Max Activating Token Index: 737

Text #17

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.3079. Min Act: 0.0000

Data Index: 1090065 (The Pile)

Max Activating Token Index: 656

Text #18

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.2876. Min Act: 0.0000

Data Index: 1830701 (The Pile)

Max Activating Token Index: 487

Text #19

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.2654. Min Act: -0.0000

Data Index: 408250 (The Pile)

Max Activating Token Index: 407